A Q-learning algorithm for task scheduling based on improved SVM in wireless sensor networks

摘要

Application performance and energy consumption deep exposed to task scheduling of nodes in wireless sensor networks (WSNs). Unreasonable task scheduling of nodes leads to excessive network energy consumption. Thus, a Q-learning algorithm for task scheduling based on Improved Support Vector Machine (ISVM) in WSNs, called ISVM-Q is proposed to optimize the application performance and energy consumption of networks. Energy consumption of task scheduling is associated with a reward of nodes in the learning process. To solve the "dimensionality disaster" problem of Q-learning, SVM is introduced as a value function approximation. Parameterizations of SVM function can strengthen the interpretation characteristics by using experience knowledge. Experiments show that ISVM-Q has the ability to make nodes perform tasks reasonably in a dynamic environment. Compared with classic task scheduling algorithms, ISVM-Q achieves better application performance with less energy consumption and keeps the learning system stable. (C) 2019 Elsevier B.V. All rights reserved.